14 Commits

Author	SHA1	Message	Date
zachcp	3159f91b90	20241118 docs (#2629) ... * module docs * varbuilder gguf docs * add a link to gguf files * small additonal mod doc titles * safetensor docs * more core docs * more module docs in canlde_core * 2 more link fixes	2024-11-19 04:07:07 +01:00
Eric Buehler	e2b6b367fa	Add some fast Metal MLX SDPA kernels (#2584) ... * Add some fast Metal MLX SDPA kernels (#32) * Sketch the sdpa kernel * Add full sdpa kernel, * Add test * Add vectorized kernel for decoding * Update tests * Add some docs * Fix sdpa_vector names * Add softcapping for vectorized sdpa * Add softcapping for full sdpa * Add support for head dim 32, 96, 256 * Add support for head dim 32, 96, 256 * Update docs * Add update notice * Clippy and format * Conditional compilation for bf16 * Use it in quantized llama * Some review comments * Use set_params! * Remove unused * Remove feature * Fix metal sdpa for v stride * Remove comma * Add the dim method to layout and shape. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com>	2024-11-05 09:28:00 +01:00
Laurent Mazare	9634583781	Expose a couple layout methods. (#1816)	2024-03-08 10:52:22 +01:00
Laurent Mazare	607ffb9f1e	Retrieve more information from PyTorch checkpoints. (#515) ... * Retrieve more information from PyTorch checkpoints. * Add enough support to load dino-v2 backbone weights.	2023-08-19 15:05:34 +01:00
Laurent Mazare	cb069d6063	Add the permute op (similar to pytorch). (#504) ... * Add the permute op (similar to pytorch). * Add the backprop for dimension permutation.	2023-08-18 16:30:53 +01:00
Laurent Mazare	acb2f90469	Broadcasting performance optimization (cpu) (#182) ... * Avoid recomputing the index from scratch each time. * More performance optimisations.	2023-07-17 13:41:09 +01:00
Laurent Mazare	18ea92d83b	Iteration over strided blocks (#175) ... * Introduce the strided blocks. * Use the strided blocks to fasten the copy. * Add more testing.	2023-07-15 21:30:35 +01:00
Laurent Mazare	d88b6cdca9	Add backtrace information to errors where relevant. (#166) ... * Add backtrace information to errors where relevant. * More backtrace information. * Add to the FAQ.	2023-07-14 09:31:25 +01:00
Laurent Mazare	a76ec797da	Cleanup the main crate error and add a couple dedicated ones (#142) ... * Cosmetic cleanups to the error enum. * More error cleanup. * Proper error handling rather than panicing. * Add some conv1d dedicated error.	2023-07-12 09:17:08 +01:00
laurent	14449ff80c	Get the cpu backend to compile.	2023-06-28 14:12:38 +01:00
laurent	54a6c40f27	Propagate the changes on the cpu backend.	2023-06-28 14:00:49 +01:00
laurent	303b853098	Propagate the layout refactoring.	2023-06-28 13:42:23 +01:00
laurent	30b355ccd2	Simplify the narrow implementation.	2023-06-28 13:09:59 +01:00
laurent	c1bbbf94f6	Start refactoring the stride.	2023-06-28 12:57:30 +01:00